DOCSLIB.ORG

Optimization of Neural Networks Through Grammatical Evolution and a Genetic Algorithm

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Optimization of Neural Networks Through Grammatical Evolution and a Genetic Algorithm Expert Systems With Applications 56 (2016) 368–384 Contents lists available at ScienceDirect Expert Systems With Applications journal homepage: www.elsevier.com/locate/eswa Optimization of neural networks through grammatical evolution and a genetic algorithm ∗ Lídio Mauro Lima de Campos a, , Roberto Célio Limão de Oliveira a, Mauro Roisenberg b a Faculty of Computer Engineering, Federal University of Pará, Rua Augusto Corrêa 01, Guamá, CEP:66075-100, Belém Caixa postal 479, Pará Brazil b Informatic and Statistic Department, Federal University of Santa Catarina, PO. Box 476, Trindade, Florianópolis 88040-900, Santa Catarina, Brazil a r t i c l e i n f o a b s t r a c t Article history: This paper proposes a hybrid neuro-evolutive algorithm (NEA) that uses a compact indirect encoding Received 17 August 2015 scheme (IES) for representing its genotypes (a set of ten production rules of a Lindenmayer System with Revised 18 January 2016 memory), moreover has the ability to reuse the genotypes and automatically build modular, hierarchi- Accepted 8 March 2016 cal and recurrent neural networks. A genetic algorithm (GA) evolves a Lindenmayer System (L-System) Available online 16 March 2016 that is used to design the neural network’s architecture. This basic neural codification confers scalability Keywords: and search space reduction in relation to other methods. Furthermore, the system uses a parallel genome Evolutionary computation scan engine that increases both the implicit parallelism and convergence of the GA. The fitness function Neural networks of the NEA rewards economical artificial neural networks (ANNs) that are easily implemented. The NEA Grammatical evolution was tested on five real-world classification datasets and three well-known datasets for time series fore- casting (TSF). The results are statistically compared against established state-of-the-art algorithms and various forecasting methods (ADANN, ARIMA, UCM, and Forecast Pro). In most cases, our NEA outper- formed the other methods, delivering the most accurate classification and time series forecasting with the least computational effort. These superior results are attributed to the improved effectiveness and efficiency of NEA in the decision-making process. The result is an optimized neural network architecture for solving classification problems and simulating dynamical systems. ©2016 Elsevier Ltd. All rights reserved. 1. Introduction Neuro-evolutive algorithms (NEAs) design and/or train ANNs through evolutionary algorithms (EAs). Bio-inspired algorithms Artificial Neural Networks (ANNs) are applied in classification (BIOAs) have gained popularity as efficient solvers of nonlinear op- ( Rivero, Dorado, Rabual, & Pazos, 2010 ), control systems ( Li, Jia, timization problems ( Krömer, Platoš, & Snášel, 2014 ). In this paper, Liu, & Ding, 2014 ), prediction ( Donate, Sanchez, & de Miguel, 2012 ), we investigate whether a new biologically inspired NEA can pro- and many other problems ( Czajkowski, Patan, & Szyma nski,´ 2014 ). vide an efficient automatic design tool for ANNs. As the network architecture depends on the class of problem to As discussed by ( Stanley & Miikkulainen, 2003 ) , the increas- be solved (classification, time series forecasting, or reinforcement ing complexity of evolutionary computation demands more so- learning), the full potential of an ANN can be exploited by optimiz- phisticated methods than direct mapping from genotype to phe- ing its architecture and training. The architecture is designed by notype , ( Dasgupta & McGregor, 1992; Donate et al., 2012; Miller, heuristic trial-and-error methods that select the transfer function Todd, & Hegde, 1989 ). An indirect encoding system (IES) allows and training algorithm for adjusting the synaptic weights. These a more compact and scalable representation than a direct encod- heuristics affect the learning and generalization capacities of the ing scheme (DES) ( Ahmadizar, Soltanian, & AkhlaghianTab, 2015; network and are usually performed by experts, who sequentially Hornby & Pollack, 2002; Lee, Seo, & Sim, 2007; Soltanian, Tab, Zar, train different topologies to determine the best architecture for a & Tsoulos, 2013; Stanley, D’Ambrosio, & Gauci, 2009 ). specific problem. To mitigate these deficiencies, researchers have Building an efficient encoding scheme for repetitive and proposed automatic procedures for these processes. recurrent structures is a challenging task for IES-based NEAs. The studies of ( Ahmadizar et al., 2015; Dasgupta & McGregor, 1992; Donate et al., 2012; Lee et al., 2007; Miller et al., 1989; ∗ Niska, Hiltunen, Karppinen, Ruuskanen, & Kolehmainen, 2004; Corresponding author. Tel.: +55 91 3201 7901. E-mail addresses: [email protected] , [email protected] (L.M.L. de Campos), Sanchez & Melin, 2014; Soltanian et al., 2013; Tsoulos, Gavrilis, [email protected] (R.C.L. de Oliveira), [email protected] (M. Roisenberg). & Glavas, 2008 ) were limited to multilayer perceptron neural http://dx.doi.org/10.1016/j.eswa.2016.03.012 0957-4174/© 2016 Elsevier Ltd. All rights reserved. L.M.L. de Campos et al. / Expert Systems With Applications 56 (2016) 368–384 369 networks (MLPs). However, dynamical systems cannot be precisely enables the reuse of phenotypic structures (rewrite of nodes and estimated by MLPs, and they require recurrent neural networks connections) at different stages of development. Such reuse is an (RNNs). NEAs evolving RNNs are rarely reported in the literature important capability of NEAs. ( Beer & Gallagher, 1992; Hornby & Pollack, 2002 ). The present Our ADEANN also utilizes expert knowledge of the problem to paper proposes that the brain manipulates recurrent subnetworks more efficiently search the infinite space of topologies, thus min- with specialized functions. Such architecture is more similar to imizing the expert’s effort in the optimization. The penalty ap- biological neural networks than feedforward neural networks and proach implemented by the fitness function ( Eq. 5 ) automatically realizes more complex computation. rewards the economical ANNs with stronger generalization and Our approach is inspired by two natural biological mechanisms: extrapolation capacities. Our L-system generates ANN topologies genetic encoding and the evolution of genetic coding. As is well- without requiring additional substrate configurations for the given known, neuron development is governed by the genetic informa- problem. In this sense, our model automates the methodology of tion encoded in deoxyribonucleic acid (DNA), and ultimately gen- ( Stanley et al., 2009 ). erates the final shape of the brain. During biological development, In addition, we investigate whether increasing or decreasing in the complex process that links the DNA code to its phenotype, the chromosome length affects the crossover rate, and conse- the same gene is used in many contexts. This compactness min- quently the number of valid production rules. Our experiments imizes the information required to describe complex individuals. confirm interference between the chromosome length, crossover On the other hand, evolution describes the temporal changes in rate, and production rules. The variable associations are discussed the genetic code (DNA). Among the several mechanisms underlying in Section 6.1 . these evolutionary changes, natural selection is very important. The next section presents state-of-the-art methodologies and The two natural processes described above are hybridized such the findings of other authors. Section 3 presents the theoretical that the DNA contained in cells can also spawn cells. On the other foundation of our work. The components of ADEANN and system hand, the changes in DNA are passed onto later generations. Mo- operation are detailed in Section 4 . Section 5 describes the materi- tivated by these natural processes, we propose an artificial hybrid als and methods and Section 6 presents the general experimental system that abstracts these natural mechanisms at an acceptable design and analyzes the computational results. A general discus- level of complexity. sion and final conclusions are presented in Sections 7 and 8 . To this end, we propose a new NEA, a biologically inspired ar- tificial hybrid system called Artificial Development and Evolution 2. State-of-the-art techniques of ANNs (ADEANN). The ADEANN integrates two components. The first is a generative representation that represents genotypes (a This section discusses existing research on NEAs. Most NEAs set of production rules of a Lindenmayer system) by a compact use DESs, which specify every connection and node in the geno- IES. The IES also conducts and controls the process of mapping type that will appear in the phenotype (ANN) . In the approaches the genotypes to the phenotypes (complex neural morphologies). proposed by Dasgupta and McGregor (1992) ; Miller et al. (1989) a To mimic the DNA encoding scheme and enable scalability, our multilayer perceptron is encoded as a directed graph, and its geno- IES leverages the phenotype representation to a smaller genotype. type is represented by an adjacency matrix . The ANN architecture Thus, the search process is carried out in a lower-dimensional solu- is evolved by the ANN itself. In other words, the chromosome en- tion space. In addition, our IES implements the organizational prin- codes all details of the network architecture. The weights of the ciples of hierarchy, modularity, and gene reuse (allowing compact neural network can then be optimized by gradient-based search representation of complex phenotypes). The
Load more

Recommended publications
  • Artificial Development of Neural-Symbolic Networks
    University of Exeter Department of Computer Science Artificial Development of Neural-Symbolic Networks Joseph Paul Townsend March 2014 Supervised by Dr. Ed Keedwell and Dr. Antony Galton Submitted by Joseph Paul Townsend, to the University of Exeter as a thesis for the degree of Doctor of Philosophy in Computer Science , March 2014. This thesis is available for Library use on the understanding that it is copyright material and that no quotation from the thesis may be published without proper acknowledgement. I certify that all material in this thesis which is not my own work has been identi- fied and that no material has previously been submitted and approved for the award of a degree by this or any other University. (signature) ................................................................................................. 1 Abstract Artificial neural networks (ANNs) and logic programs have both been suggested as means of modelling human cognition. While ANNs are adaptable and relatively noise resis- tant, the information they represent is distributed across various neurons and is therefore difficult to interpret. On the contrary, symbolic systems such as logic programs are in- terpretable but less adaptable. Human cognition is performed in a network of biological neurons and yet is capable of representing symbols, and therefore an ideal model would combine the strengths of the two approaches. This is the goal of Neural-Symbolic In- tegration [4, 16, 21, 40], in which ANNs are used to produce interpretable, adaptable representations of logic programs and other symbolic models. One neural-symbolic model of reasoning is SHRUTI [89, 95], argued to exhibit biological plausibility in that it captures some aspects of real biological processes.
    [Show full text]
  • A Novel Generative Encoding for Evolving Modular, Regular and Scalable Networks
    A Novel Generative Encoding for Evolving Modular, Regular and Scalable Networks Marcin Suchorzewski Jeff Clune Artificial Intelligence Laboratory Creative Machines Laboratory West Pomeranian University of Technology Cornell University [email protected] [email protected] ABSTRACT 1. INTRODUCTION In this paper we introduce the Developmental Symbolic En- Networks designed by humans and evolution have certain coding (DSE), a new generative encoding for evolving net- properties that are thought to enhance both their perfor- works (e.g. neural or boolean). DSE combines elements of mance and adaptability, such as modularity, regularity, hier- two powerful generative encodings, Cellular Encoding and archy, scalability, and being scale-free [12, 11, 1]. In this pa- HyperNEAT, in order to evolve networks that are modular, per we introduce a new generative representation called the regular, scale-free, and scalable. Generating networks with Developmental Symbolic Encoding that evolves networks these properties is important because they can enhance per- that possess these properties. We first review the mean- formance and evolvability. We test DSE’s ability to gener- ing of these terms before discussing them with respect to ate scale-free and modular networks by explicitly rewarding previous evolutionary algorithms. these properties and seeing whether evolution can produce Modularity is the encapsulation of function within mostly networks that possess them. We compare the networks DSE independently operating units, where the internal workings evolves to those of HyperNEAT. The results show that both of the module tend to only affect the rest of the structure encodings can produce scale-free networks, although DSE through the module’s inputs and outputs [12, 11].
    [Show full text]
  • Artificial Biochemical Networks : Evolving Dynamical Systems to Control Dynamical Systems
    This is a repository copy of Artificial Biochemical Networks : Evolving Dynamical Systems to Control Dynamical Systems. White Rose Research Online URL for this paper: https://eprints.whiterose.ac.uk/75277/ Version: Accepted Version Article: Lones, Michael Adam, Fuente, Luis Alberto, Turner, Alexander Phillip et al. (4 more authors) (2014) Artificial Biochemical Networks : Evolving Dynamical Systems to Control Dynamical Systems. IEEE Transactions on Evolutionary Computation. 6423886. pp. 145- 166. ISSN 1089-778X https://doi.org/10.1109/tevc.2013.2243732 Reuse Items deposited in White Rose Research Online are protected by copyright, with all rights reserved unless indicated otherwise. They may be downloaded and/or printed for private study, or other acts as permitted by national copyright laws. The publisher or other rights holders may allow further reproduction and re-use of the full text version. This is indicated by the licence information on the White Rose Research Online record for the item. Takedown If you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing [email protected] including the URL of the record and the reason for the withdrawal request. [email protected] https://eprints.whiterose.ac.uk/ IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, PREPRINT, ACCEPTED FOR PUBLICATION DECEMBER 2012 1 Artificial Biochemical Networks: Evolving Dynamical Systems to Control Dynamical Systems Michael A. Lones, Senior Member, IEEE, Luis A. Fuente, Alexander P. Turner, Leo S. D. Caves, Susan Stepney, Stephen L. Smith, Member, IEEE, and Andy M. Tyrrell, Senior Member, IEEE Abstract—Biological organisms exist within environments in different evolutionary algorithms have been used to design which complex, non-linear dynamics are ubiquitous.
    [Show full text]
  • Artificial Intelligence Vs (General) Artificial Intelligence 3
    ISSN 0798 1015 HOME Revista ESPACIOS ÍNDICES / Index A LOS AUTORES / To the ! ! AUTORS ! Vol. 40 (Number 4) Year 2019. Page 3 ¿Will machines ever rule the world? ¿Las máquinas dominarán el mundo? PEDROZA, Mauricio 1; VILLAMIZAR, Gustavo 2; MENDEZ, James 3 Received: 11/08/2018 • Approved: 16/12/2018 • Published 04/02/2019 Contents 1. Introduction 2. (Narrow) Artificial Intelligence vs (General) Artificial Intelligence 3. Machines designed as tools of man 4. Machines thought as similar to man 5. Conclusions Acknowledgments Bibliographic references ABSTRACT: RESUMEN: From ancient automatons, to the latest technologies Desde los antiguos autómatas hasta las últimas of robotics and supercomputing, the continued tecnologías de la robótica, el continuo progreso de la progress of mankind has led man to even question his humanidad ha llevado al hombre a cuestionar incluso future status as a dominant species. “Will machines su estatus futuro como especie dominante. "¿Alguna ever rule the world?” or more precisely: Do we want vez dominarán las máquinas el mundo?" O más machines to rule the world? Theoretical and precisamente: ¿Queremos que las máquinas dominen technological challenges involved in this choice will be el mundo? Los retos teóricos y tecnológicos que se considered both under the conservative approach of plantean en esta elección serán considerados tanto "machines designed as tools of man" and in the bajo el enfoque conservador de "máquinas que sirven scenario of "machines thought as similar to man". al hombre" como en el escenario de "máquinas Keywords: Artificial Intelligence, Cognitive Machines, equiparables al hombre" Narrow Artificial Intelligence Strong Artificial Palabras clave: Inteligencia Artificial, Máquinas Intelligence, Artificial General Intelligence.
    [Show full text]
  • Artificial Intelligence and Broadband Divide
    Artificial Intelligence and Broadband Divide State of ict Connectivity in Asia and the Pacific 2017 The Economic and Social Commission for Asia and the Pacific (ESCAP) serves as the United Nations’ regional hub promoting cooperation among countries to achieve inclusive and sustainable development. The largest regional intergovernmental platform with 53 Member States and 9 associate members, ESCAP has emerged as a strong regional think-tank offering countries sound analytical products that shed insight into the evolving economic, social and environmental dynamics of the region. The Commission’s strategic focus is to deliver on the 2030 Agenda for Sustainable Development, which it does by reinforcing and deepening regional cooperation and integration to advance connectivity, financial cooperation and market integration. ESCAP’s research and analysis coupled with its policy advisory services, capacity building and technical assistance to governments aims to support countries’ sustainable and inclusive development ambitions. The shaded areas of the map indicate ESCAP members and associate members. Information and statistics presented in this publication include only those member and associate member States located in the Asia-Pacific region. Disclaimer: This report of the Information and Communications Technology and Disaster Risk Reduction Division provides policy-relevant analysis on regional trends and challenges in support of the development of the Asia-Pacific Information Superhighway and inclusive development. The views expressed herein are those of the authors, and do not necessarily reflect the views of the United Nations. This report has been issued without formal editing, and the designations employed and material presented do not imply the expression of any opinion whatsoever on the part of the Secretariat of the United Nations concerning the legal status of any country, territory, city or area, or of its authorities, or concerning the delimitation of its frontiers or boundaries.
    [Show full text]
  • Building Processes Optimization : Toward an Artificial Ontogeny Based Approach
    Building processes optimization : Toward an artificial ontogeny based approach Alexandre Devert Directed by Marc Schoenauer and Nicolas Bred`eche Submitted in total fulfilment of the requirements of the degree of Doctor of Philosophy June 21, 2009 Ecole Doctorale d’Informatique Universit´eParis-Sud 11 Contents 1 Introduction to Evolutionary Design 5 1.1 Anevolutionaryalgorithmsprimer . 7 1.1.1 Description .......................... 8 1.1.2 Lamarckian and Baldwinian evolutions . 9 1.1.3 Onthe designof anevolutionaryalgorithm . 10 1.2 Simulationandevaluation . 11 1.2.1 Designofanevaluationfunction . 13 1.2.2 Theusageofsimulation . 14 1.3 Representations for Evolutionary Design . .. 15 1.3.1 Blockstacks.......................... 15 1.3.2 Explicit and implicit representations . 18 1.3.3 Modularity .......................... 19 1.3.4 Treestructures .. .. .. .. .. .. .. .. .. .. 21 1.3.5 Grammarsandrewritingsystems . 23 1.3.6 Theevolvabilityissue . 26 1.3.7 Cellularrepresentations . 26 1.4 Preview ................................ 29 2 AguidedtourofEvolutionaryDesign 31 2.1 Explicitrepresentations . 31 2.1.1 Blockstacks.......................... 31 2.1.2 Legostructures.. .. .. .. .. .. .. .. .. .. 32 2.1.3 Antennae ........................... 33 2.1.4 Shapes............................. 34 2.1.5 Robots............................. 35 2.1.6 Tensegritystructures. 36 2.1.7 TopologicalOptimumDesign . 37 2.1.8 Opticalfibersdesign . 38 2.1.9 Bladeshapedesignforwindturbines. 39 2.2 Implicitrepresentations . 40 2.2.1 KarlSims’creatures . 40 2.2.2 Hornby’sL-systems . 41 2.2.3 EnvironmentawareL-systems. 44 2.3 Cellularrepresentations . 45 2.3.1 Virtualcreatures . 46 2.3.2 Skyscraperframes . 47 2.3.3 Trussstructures . .. .. .. .. .. .. .. .. .. 48 2.3.4 Environmentawareness . 50 2.4 Conclusion .............................. 51 1 CONTENTS 3 An Evolutionary algorithm for blueprints 55 3.1 TheBlindBuilderrepresentation . 55 3.1.1 Variationoperators. 57 3.2 Designofsimple3dobjects .
    [Show full text]
  • Evolving Gene Expression to Reconfigure Analogue Devices
    EVOLVING GENE EXPRESSION TO RECONFIGURE ANALOGUE DEVICES Kester Dean Clegg Thesis submitted in partial fulfilment of the requirements for the degree of Doctor of Philosophy. Department of Computer Science May, 2008 Abstract Repeated, morphological functionality, from limbs to leaves, is widespread in nature. Pattern formation in early embryo development has shed light on how and why the same genes are expressed in different locations or at different times. Practitioners working in evolutionary computation have long regarded nature’s reuse of modular functionality with admiration. But repeating na- ture’s trick has proven difficult. To date, no one has managed to evolve the design for a car, a house or a plane. Or indeed anything where the number of interdependent parts exposed to random mutation is large. It seems that while we can use evolutionary algorithms for search-based optimisation with great success, we cannot use them to tackle large, complex designs where functional reuse is essential. This thesis argues that the modular functionality provided by gene reuse could play an important part in evolutionary computation being able to scale, and that by expressing subsets of genes in specific contexts, successive stages of phenotype configuration can be controlled by evolutionary search. We present a conceptual model of context-specific gene expression and show how a ge- nome representation can hold many genes, only a few of which need be ex- pressed in a solution. As genes are expressed in different contexts, their func- tional role in a solution changes. By allowing gene expression to discover phe- notype solutions, evolutionary search can guide itself across multiple search domains.
    [Show full text]
  • Melomics: a Case-Study of AI in Spain Research Groups in the Spanish Computer Sci - Ences
    Column Worldwide AI Australia Spain n Traditionally focused on good old-fashioned Carlos Sánchez Quintana, Francisco Moreno Arcas, David Albar - AI and robotics, the Spanish AI community holds a vigorous computational intelligence racín Molina, Jose David Fernández Rodríguez, Francisco J. Vico substrate. Neuromorphic, evolutionary, or fuzzylike systems have been developed by many Melomics: A Case-Study of AI in Spain research groups in the Spanish computer sci - ences. It is no surprise, then, that these nature- grounded efforts start to emerge, enriching the In Spain there are 74 universities, many of which have computer sci - AI catalogue of research projects and publica - ence departments that host AI-related research groups. AEPIA, the tions and, eventually, leading to new directions Spanish society for AI research, was founded in 1983 and has been of basic or applied research. In this article, we vigorously promoting the advancement of AI since then. Along with review the contribution of Melomics in compu - several other societies and communities of interest, it promotes var - tational creativity. ious periodic conferences and workshops. The Artificial Intelligence Research Institute (IIIA) of the Spanish National Research Council constitutes one of the flagships of local AI research. Ramón López de Mántaras, IIIA’s renowned director, was one of the pioneers of AI in Spain, and he also was the recipient of the prestigious AAAI Engle - more Award in 2011. Other researchers that have reached an out - standing position, and lead important research groups in Spain, include Antonio Bahamonde (University of Oviedo), Federico Barber (Polytechnic University of Madrid), Vicent Botti (Polytechnic Uni - versity of Valencia), and Amparo Vila (University of Granada).
    [Show full text]
  • A Review of Morphogenetic Engineering (Running Title: a Review of Morphogenetic Engineering)
    A Review of Morphogenetic Engineering (Running title: A Review of Morphogenetic Engineering) Ren´eDoursat*1, Hiroki Sayama2, and Olivier Michel3 1School of Biomedical Engineering, Drexel University 3141 Chestnut Street, Philadelphia, PA 19104, US ([email protected]) *corresp. author 2Department of Bioengineering, Binghamton University SUNY PO Box 6000, Binghamton, NY 13902, US ([email protected]) 3Facult´edes Sciences et Technologie, Universit´ede Cr´eteil 61, ave du G´en´eral de Gaulle, 94010 Cr´eteilCedex, France ([email protected]) Abstract Generally, phenomena of spontaneous pattern formation are random and repetitive, whereas elaborate devices are the deterministic product of human design. Yet, biological organisms and collective insect constructions are exceptional examples of complex systems that are both ar- chitectured and self-organized. Can we understand their precise self-formation capabilities and integrate them with technological planning? Can physical systems be endowed with informa- tion, or informational systems be embedded in physics, to create autonomous morphologies and functions? To answer these questions, we have launched in 2009, and developed through a series of workshops and a collective book, a new field of research called Morphogenetic Engi- neering. It is the first initiative of its kind to rally and promote models and implementations of complex self-architecturing systems. Particular emphasis is set on the programmability and com- putational abilities of self-organization, properties that are often underappreciated in complex systems science|while, conversely, the benefits of self-organization are often underappreciated in engineering methodologies1. Keywords: agent-based modeling, artificial life, collective construction, complex systems, evo- lutionary development, generative grammars, morphogenesis, self-organization, swarm robotics, systems engineering.
    [Show full text]
  • Hello, World: Artificial Intelligence and Its Use in the Public Sector
    Hello, World: Artificial intelligence and its use in the public sector Jamie Berryhill Kévin Kok Heang Rob Clogher Keegan McBride November 2019 | http://oe.cd/helloworld OECD Working Papers on Public Governance No. 36 Cover images are the European Parliament and the dome of Germany’s Reichstag building processed through Deep Learning algorithms to match the style of Van Gogh paintings. tw Hello, World: Artificial Intelligence and its Use in the Public Sector Authors: Jamie Berryhill, Kévin Kok Heang, Rob Clogher, Keegan McBride PUBE 2 This document and any map included herein are without prejudice to the status of or sovereignty over any territory, to the delimitation of international frontiers and boundaries and to the name of any territory, city or area. 1. Note by Tukey: The information in this document with reference to ‘Cyprus’ relates to the southern part of the island. There is no single authority representing both Turkish and Greek Cypriot people on the island. Turkey recognises the Turkish Republic of Northern Cyprus (TRNC). Until a lasting and equitable solution is found within the context of the United Nations, Turkey shall preserve its position concerning the ‘Cyprus issue’. 2. Note by all the European Union Member States of the OECD and the European Commission: The Republic of Cyprus is recognised by all members of the United Nations with the exception of Turkey. The information in this document relates to the area under the effective control of the Government of the Republic of Cyprus. HELLO, WORLD: ARTIFICIAL INTELLIGENCE AND ITS USE IN THE PUBLIC SECTOR © OECD 2019 3 Foreword Artificial Intelligence (AI) is an area of research and technology application that can have a significant impact on public policies and services in many ways.
    [Show full text]
  • Phenotypic, Developmental and Computational Resources: Scaling in Artificial Development
    Phenotypic, Developmental and Computational Resources: Scaling in Artificial Development Gunnar Tufte Norwegian University of Science and Technology Department of Computer and Information Science Sem Selandsvei 7-9 7491 Trondheim Norway [email protected] ABSTRACT Algorithms (EAs) is the aspect of scalability. In the work Developmental systems have inherent properties favourable of Kitano [20] the scaling issue was addressed by searching for scaling. The possibility to generate very large scale for an effective encoding in order to generate more complex structures combined with gene regulation opens for systems network structures. The urge towards evolution of complex where the genome size do not reflect the size and complexity network structures was motivated by a need to handle scal- of the phenotype. Despite the presence of scalability in na- ing of the complexity of solvable problems. ture there is limited knowledge of what makes a developmen- The proposed solution was a developmental system i.e. an tal mapping scalable. As such, there is few artificial system indirect mapping. In contrast, in a direct mapping approach that show true scaling. Scaling for any system, biological there is a single phenotype, defined by the genotype. This or artificial, is a question of resources. Toward an under- implies that each element in the phenotype is represented ex- standing of the challenges of scalability the issue of scaling plicitly in the genotype. As such, introducing mechanisms, is investigated in an aspect of resources within the develop- inspired by development, into evolutionary computation was mental model itself. The resources are decompositioned into motivated by a need to overcome limitations in such direct domains that can be scaled separately each may influence on mapping approaches, e.g.
    [Show full text]
  • Artificial Development
    ARTIFICIAL DEVELOPMENT Simon Harding and Wolfgang Banzhaf1 1 Department of Computer Science, Memorial University Abstract There is growing interest in the use of analogies of biological development for problem solving in computer science. Nature is extremely intricate when com- pared to human designs, and incorporates features such as the ability to scale, adapt and self-repair that could be usefully incorporated into human-designed artifacts. In this chapter, we discuss how the metaphor of biological develop- ment can be used in artificial systems and highlight some of the challenges of this emerging field. Keywords: Developmental systems, genetic algorithms, pattern formation 1. Introduction Organic processes can serve as inspiration for computational systems. The design and functionality of organic systems is both a challenge and an exis- tence proof of achievements of Nature posed to the human designer. In this context it has turned out that the level of complexity commanded in the design of natural systems is still unparalleled. To put the scalability of biological sys- tems into perspective: Microsoft’s latest version of Windows has 106 lines of code, some Linux distributions have 107 lines of computer code, but there are 1014 cells in the human body each much more complex than a line of code. Such complexity would be out of reach of human designers, who even struggle to keep the simplest designs and manufacturing processes defect-free. With the increasing complexity of both hardware and software, there is need is growing for new design techniques that allow us to work with such complexity. Evolutionary algorithms that mimic Darwinian evolution have provided part of the answer to this problem.
    [Show full text]